Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2198 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.0838. Min Range: -4.0838

Max Act: 4.0838. Min Act: -0.1700

Data Index: 2138606 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 4.0838. Min Range: -4.0838

Max Act: 3.9988. Min Act: -0.1700

Data Index: 8675679 (Open Web Text)

Max Activating Token Index: 13

Text #2

Max Range: 4.0838. Min Range: -4.0838

Max Act: 3.9678. Min Act: -0.1700

Data Index: 2773954 (Open Web Text)

Max Activating Token Index: 17

Text #3

Max Range: 4.0838. Min Range: -4.0838

Max Act: 3.9525. Min Act: -0.1700

Data Index: 566754 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 4.0838. Min Range: -4.0838

Max Act: 3.9658. Min Act: -0.1700

Data Index: 1333223 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 4.0838. Min Range: -4.0838

Max Act: 3.9515. Min Act: -0.1700

Data Index: 3413922 (Open Web Text)

Max Activating Token Index: 10

Text #6

Max Range: 4.0838. Min Range: -4.0838

Max Act: 3.9478. Min Act: -0.1700

Data Index: 3445876 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 4.0838. Min Range: -4.0838

Max Act: 3.9640. Min Act: -0.1700

Data Index: 8499613 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 4.0838. Min Range: -4.0838

Max Act: 3.9572. Min Act: -0.1700

Data Index: 6615153 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 4.0838. Min Range: -4.0838

Max Act: 3.9466. Min Act: -0.1700

Data Index: 6439190 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 4.0838. Min Range: -4.0838

Max Act: 3.9307. Min Act: -0.1700

Data Index: 8819946 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 4.0838. Min Range: -4.0838

Max Act: 3.9367. Min Act: -0.1700

Data Index: 2304526 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 4.0838. Min Range: -4.0838

Max Act: 3.9347. Min Act: -0.1700

Data Index: 2608845 (Open Web Text)

Max Activating Token Index: 8

Text #13

Max Range: 4.0838. Min Range: -4.0838

Max Act: 3.9349. Min Act: -0.1700

Data Index: 5122639 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 4.0838. Min Range: -4.0838

Max Act: 3.9039. Min Act: -0.1700

Data Index: 6438249 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 4.0838. Min Range: -4.0838

Max Act: 3.8946. Min Act: -0.1700

Data Index: 5499722 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 4.0838. Min Range: -4.0838

Max Act: 3.8929. Min Act: -0.1700

Data Index: 378074 (Open Web Text)

Max Activating Token Index: 13

Text #17

Max Range: 4.0838. Min Range: -4.0838

Max Act: 3.9153. Min Act: -0.1700

Data Index: 2350159 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 4.0838. Min Range: -4.0838

Max Act: 3.9001. Min Act: -0.1700

Data Index: 1025319 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 4.0838. Min Range: -4.0838

Max Act: 3.8956. Min Act: -0.1700

Data Index: 2601008 (Open Web Text)

Max Activating Token Index: 7